ai-coding-dictionary
Skill0 starsChanged 3 months agoMITView on GitHub
Use when the user asks about AI coding jargon, wants to clarify a term like context engineering, harness engineering, prompt engineering, or agent harness, or when the agent needs to agree on a term definition before continuing a technical discussion.
In this repository110 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/project-bootstrap/templates/agents.mdAGENTS.md
- a11y-auditSkill
- agentic-ragSkill
- agent-reachSkill
- ai3d-genSkill
- ai-toolsSkill
- animation-directionSkill
- api-specSkill
- architecture-diagramsSkill
- architectureSkill
- ascii-artSkill
- ask-bundleSkill
- binary-triageSkill
- bragSkill
- brag-slimSkill
- career-opsSkill
- code-reviewSkill
- computer-useSkill
- context7Skill
- context-hygieneSkill
- creative-engineeringSkill
- cu-realtimeSkill
- data-analystSkill
- databaseSkill
- dead-wireSkill
- debuggingSkill
- deploySkill
- devin-configSkill
- dispatching-parallel-agentsSkill
- dmaSkill
- dockerSkill
- drift-reportSkill
- e2e-testingSkill
- edge-casesSkill
- executionSkill
- fact-checkSkill
- finishing-a-development-branchSkill
- firmware-probeSkill
- frontend-designSkill
- gatesSkill
- ghidraSkill
- ghSkill
- github-actionsSkill
- git-workflowsSkill
- grillingSkill
- handoffSkill
- humanizerSkill
- hyperframesSkill
- i18nSkill
- image-forensicsSkill
- impeccableSkill
- implement-layaSkill
- intakeSkill
- jiraSkill
- knowledge-modelingSkill
- laya-orchestratorSkill
- learn-modeSkill
- mcp-governanceSkill
- media-toolsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
If the term is not in the dictionary and you cannot define it confidently, invoke research to find primary sources first.
- Very specific: line 27
Use research when the dictionary does not yet contain the term and you need authoritative sources.
- Very specific: line 28
Use teach when the user wants a full lesson instead of a one-line definition.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Coding Dictionary
Overview
AI coding has a growing set of overloaded terms. This skill resolves them by pointing to the canonical definitions in docs/AI-CODING-DICTIONARY.md.
When to use
- User asks "what is X?" about an AI coding term.
- You are about to use a term (e.g., "harness engineering") and want to confirm the user shares the definition.
- A conversation is drifting because a term is being used loosely.
How to use
- Read
docs/AI-CODING-DICTIONARY.md. - Find the term. If it is missing, add a tight definition following the existing format (one or two sentences, flag ambiguities, list what to avoid).
- Quote the definition to the user and ask if they want to add, edit, or remove any nuance.
- If the term is not in the dictionary and you cannot define it confidently, invoke
researchto find primary sources first.
Cross-skills
- Use
researchwhen the dictionary does not yet contain the term and you need authoritative sources. - Use
teachwhen the user wants a full lesson instead of a one-line definition.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

